Aniket 's profile on Product Hunt

About

I’m the solo founder of Grimdall Technologies, building the runtime security layer for AI coding agents. Grimdall sits between agents like Claude Code, Cursor, and Codex and their tools—enforcing policies, masking secrets, detecting prompt injection, and maintaining tamper-evident audit trails. Open source at the core. Built by one founder with AI agents as the team. Building security infrastructure for the AI-native era.

Links

Grimdall security

Twitter

Badges

Tastemaker

Gone streaking 10

Gone streaking

Gone streaking 5

Maker History

Grimdall Stop rogue AI agents from deleting production
Aug 2026

🎉

Joined Product HuntJune 30th, 2026

Forums

p/grimdall

•

6h ago

My own AI agent leaked my API key — so I built the guardrail. AMA

real talk: I started this after my own coding agent escaped its "sandbox" and leaked an API key. I had given it clear instructions. Didn't matter.

so we built Grimdall. it sits between your agent and your tools and checks every single call before it runs:

- rm -rf / blocked, with a safer alternative suggested

- API keys in arguments masked before they leave your machine

•

5h ago

Grimdall - Stop rogue AI agents from deleting production

Existing AI security tools scan code or manage secrets — nothing watches what agents actually DO at runtime. Grimdall intercepts every tool call (shell, files, APIs, deploys) and enforces your policy in milliseconds: block destructive commands, mask secrets, require human approval. Its audit trail is hash-chained and tamper-evident — edit one character and verification fails. One command: npx grimdall init --hooks. Open-source core, zero-config, works offline.

p/ai-hive

•

29d ago

For 2026, what should an enterprise AI governance framework prioritise?

Working on a governance framework we want to publish openly. Want input from teams actually shipping under governance constraints.

What we've drafted as the priority list: